nokogiri 1.0.0 → 1.6.8.1

data/lib/nokogiri/css/generated_tokenizer.rb

@@ -1,159 +0,0 @@
-#
-# DO NOT MODIFY!!!!
-# This file is automatically generated by rex 1.0.1
-# from lexical definition file "lib/nokogiri/css/tokenizer.rex".
-#
-
-module Nokogiri
-module CSS
-class GeneratedTokenizer
-  require 'strscan'
-
-  class ScanError < StandardError ; end
-
-  attr_reader :lineno
-  attr_reader :filename
-
-  def scan_setup ; end
-
-  def action &block
-    yield
-  end
-
-  def scan_str( str )
-    scan_evaluate  str
-    do_parse
-  end
-
-  def load_file( filename )
-    @filename = filename
-    open(filename, "r") do |f|
-      scan_evaluate  f.read
-    end
-  end
-
-  def scan_file( filename )
-    load_file  filename
-    do_parse
-  end
-
-  def next_token
-    @rex_tokens.shift
-  end
-
-  def scan_evaluate( str )
-    scan_setup
-    @rex_tokens = []
-    @lineno  =  1
-    ss = StringScanner.new(str)
-    state = nil
-    until ss.eos?
-      text = ss.peek(1)
-      @lineno  +=  1  if text == "\n"
-      case state
-      when nil
-        case
-        when (text = ss.scan(/~=/i))
-           @rex_tokens.push action { [:INCLUDES, text] }
-
-        when (text = ss.scan(/\|=/i))
-           @rex_tokens.push action { [:DASHMATCH, text] }
-
-        when (text = ss.scan(/\^=/i))
-           @rex_tokens.push action { [:PREFIXMATCH, text] }
-
-        when (text = ss.scan(/\$=/i))
-           @rex_tokens.push action { [:SUFFIXMATCH, text] }
-
-        when (text = ss.scan(/\*=/i))
-           @rex_tokens.push action { [:SUBSTRINGMATCH, text] }
-
-        when (text = ss.scan(/!=/i))
-           @rex_tokens.push action { [:NOT_EQUAL, text] }
-
-        when (text = ss.scan(/[-]?([_a-z]|[^\0-\177]|\\[0-9a-f]{1,6}(\r\n|[\s\n\r\t\f])?|\\[^\n\r\f0-9a-f])([_a-z0-9-]|[^\0-\177]|\\[0-9a-f]{1,6}(\r\n|[\s\n\r\t\f])?|\\[^\n\r\f0-9a-f])*\(\s*/i))
-           @rex_tokens.push action { [:FUNCTION, text] }
-
-        when (text = ss.scan(/@[-]?([_a-z]|[^\0-\177]|\\[0-9a-f]{1,6}(\r\n|[\s\n\r\t\f])?|\\[^\n\r\f0-9a-f])([_a-z0-9-]|[^\0-\177]|\\[0-9a-f]{1,6}(\r\n|[\s\n\r\t\f])?|\\[^\n\r\f0-9a-f])*/i))
-           @rex_tokens.push action { [:IDENT, text] }
-
-        when (text = ss.scan(/[-]?([_a-z]|[^\0-\177]|\\[0-9a-f]{1,6}(\r\n|[\s\n\r\t\f])?|\\[^\n\r\f0-9a-f])([_a-z0-9-]|[^\0-\177]|\\[0-9a-f]{1,6}(\r\n|[\s\n\r\t\f])?|\\[^\n\r\f0-9a-f])*/i))
-           @rex_tokens.push action { [:IDENT, text] }
-
-        when (text = ss.scan(/-?([0-9]+|[0-9]*\.[0-9]+)/i))
-           @rex_tokens.push action { [:NUMBER, text] }
-
-        when (text = ss.scan(/\#([_a-z0-9-]|[^\0-\177]|\\[0-9a-f]{1,6}(\r\n|[\s\n\r\t\f])?|\\[^\n\r\f0-9a-f])+/i))
-           @rex_tokens.push action { [:HASH, text] }
-
-        when (text = ss.scan(/[\s\r\n\f]*\+/i))
-           @rex_tokens.push action { [:PLUS, text] }
-
-        when (text = ss.scan(/[\s\r\n\f]*>/i))
-           @rex_tokens.push action { [:GREATER, text] }
-
-        when (text = ss.scan(/[\s\r\n\f]*,/i))
-           @rex_tokens.push action { [:COMMA, text] }
-
-        when (text = ss.scan(/[\s\r\n\f]*~/i))
-           @rex_tokens.push action { [:TILDE, text] }
-
-        when (text = ss.scan(/\:not\(/i))
-           @rex_tokens.push action { [:NOT, text] }
-
-        when (text = ss.scan(/@[-]?([_a-z]|[^\0-\177]|\\[0-9a-f]{1,6}(\r\n|[\s\n\r\t\f])?|\\[^\n\r\f0-9a-f])([_a-z0-9-]|[^\0-\177]|\\[0-9a-f]{1,6}(\r\n|[\s\n\r\t\f])?|\\[^\n\r\f0-9a-f])*/i))
-           @rex_tokens.push action { [:ATKEYWORD, text] }
-
-        when (text = ss.scan(/-?([0-9]+|[0-9]*\.[0-9]+)%/i))
-           @rex_tokens.push action { [:PERCENTAGE, text] }
-
-        when (text = ss.scan(/-?([0-9]+|[0-9]*\.[0-9]+)[-]?([_a-z]|[^\0-\177]|\\[0-9a-f]{1,6}(\r\n|[\s\n\r\t\f])?|\\[^\n\r\f0-9a-f])([_a-z0-9-]|[^\0-\177]|\\[0-9a-f]{1,6}(\r\n|[\s\n\r\t\f])?|\\[^\n\r\f0-9a-f])*/i))
-           @rex_tokens.push action { [:DIMENSION, text] }
-
-        when (text = ss.scan(/<!--/i))
-           @rex_tokens.push action { [:CDO, text] }
-
-        when (text = ss.scan(/-->/i))
-           @rex_tokens.push action { [:CDC, text] }
-
-        when (text = ss.scan(/[\s\r\n\f]*\/\//i))
-           @rex_tokens.push action { [:DOUBLESLASH, text] }
-
-        when (text = ss.scan(/[\s\r\n\f]*\//i))
-           @rex_tokens.push action { [:SLASH, text] }
-
-        when (text = ss.scan(/U\+[0-9a-f?]{1,6}(-[0-9a-f]{1,6})?/i))
-           @rex_tokens.push action {[:UNICODE_RANGE, text] }
-
-        when (text = ss.scan(/\/\*(.|[\r\n])*?\*\//i))
-          ;
-
-        when (text = ss.scan(/[\s\t\r\n\f]+/i))
-           @rex_tokens.push action { [:S, text] }
-
-        when (text = ss.scan(/[\.*:\[\]=\)]/i))
-           @rex_tokens.push action { [text, text] }
-
-        when (text = ss.scan(/"([^\n\r\f"]|\\n|\r\n|\r|\f|[^\0-\177]|\\[0-9a-f]{1,6}(\r\n|[\s\n\r\t\f])?|\\[^\n\r\f0-9a-f])*"|'([^\n\r\f']|\\n|\r\n|\r|\f|[^\0-\177]|\\[0-9a-f]{1,6}(\r\n|[\s\n\r\t\f])?|\\[^\n\r\f0-9a-f])*'/i))
-           @rex_tokens.push action { [:STRING, text] }
-
-        when (text = ss.scan(/\"([^\n\r\f\"]|\\n|\r\n|\r|\f|[^\0-\177]|\\[0-9a-f]{1,6}(\r\n|[\s\n\r\t\f])?|\\[^\n\r\f0-9a-f])*|([^\n\r\f\']|\\n|\r\n|\r|\f|[^\0-\177]|\\[0-9a-f]{1,6}(\r\n|[\s\n\r\t\f])?|\\[^\n\r\f0-9a-f])*/i))
-           @rex_tokens.push action { [:INVALID, text] }
-
-        when (text = ss.scan(/./i))
-           @rex_tokens.push action { [text, text] }
-
-        else
-          text = ss.string[ss.pos .. -1]
-          raise  ScanError, "can not match: '" + text + "'"
-        end  # if
-
-      else
-        raise  ScanError, "undefined state: '" + state.to_s + "'"
-      end  # case state
-    end  # until ss
-  end  # def scan_evaluate
-
-end # class
-end
-end

data/lib/nokogiri/decorators/hpricot/node.rb

@@ -1,58 +0,0 @@
-module Nokogiri
-  module Decorators
-    module Hpricot
-      module Node
-        def search *paths
-          ns = paths.last.is_a?(Hash) ? paths.pop : {}
-          converted = paths.map { |path|
-            convert_to_xpath(path)
-          }.flatten.uniq
-
-          namespaces = document.xml? ? document.namespaces.merge(ns) : ns
-          super(*converted + [namespaces])
-        end
-        def /(path); search(path) end
-
-        def xpath *args
-          return super if args.length > 0
-          path
-        end
-
-        def raw_attributes; self end
-
-        def get_element_by_id element_id
-          search("//*[@id='#{element_id}']").first
-        end
-
-        def get_elements_by_tag_name tag
-          search("//#{tag}")
-        end
-
-        def convert_to_xpath(rule)
-          rule = rule.to_s
-          case rule
-          when %r{^//}
-            [".#{rule}"]
-          when %r{^/}
-            [rule]
-          when %r{^.//}
-            [rule]
-          else
-            ctx = CSS::Parser.parse(rule)
-            visitor = CSS::XPathVisitor.new
-            visitor.extend(Hpricot::XPathVisitor)
-            ctx.map { |ast| './/' + visitor.accept(ast.preprocess!) }
-          end
-        end
-
-        def target
-          name
-        end
-
-        def to_original_html
-          to_html
-        end
-      end
-    end
-  end
-end

data/lib/nokogiri/decorators/hpricot/node_set.rb

@@ -1,14 +0,0 @@
-module Nokogiri
-  module Decorators
-    module Hpricot
-      module NodeSet
-        def filter rule
-          ctx = CSS::Parser.parse(rule.to_s)
-          visitor = CSS::XPathVisitor.new
-          visitor.extend(Hpricot::XPathVisitor)
-          search('.//self::' + visitor.accept(ctx.first))
-        end
-      end
-    end
-  end
-end

data/lib/nokogiri/decorators/hpricot/xpath_visitor.rb

@@ -1,17 +0,0 @@
-module Nokogiri
-  module Decorators
-    module Hpricot
-      ####
-      # This mixin does custom adjustments to deal with _whyML
-      module XPathVisitor
-        def visit_attribute_condition node
-          unless (node.value.first.type == :FUNCTION) or (node.value.first.value.first =~ /^@/)
-            node.value.first.value[0] = "child::" +
-              node.value.first.value[0]
-          end
-          super(node).gsub(/child::text\(\)/, 'normalize-space(child::text())')
-        end
-      end
-    end
-  end
-end

data/lib/nokogiri/decorators/hpricot.rb

@@ -1,3 +0,0 @@
-require 'nokogiri/decorators/hpricot/node'
-require 'nokogiri/decorators/hpricot/node_set'
-require 'nokogiri/decorators/hpricot/xpath_visitor'

data/lib/nokogiri/decorators.rb

@@ -1 +0,0 @@
-require 'nokogiri/decorators/hpricot'

data/lib/nokogiri/hpricot.rb

@@ -1,47 +0,0 @@
-require 'nokogiri'
-
-module Nokogiri
-  module Hpricot
-    STag = String
-    Elem = XML::Node
-    NamedCharacters = Nokogiri::HTML::NamedCharacters
-    class << self
-      def parse(*args)
-        doc = Nokogiri.parse(*args)
-        add_decorators(doc)
-      end
-
-      def XML(string)
-        doc = Nokogiri::XML.parse(string)
-        add_decorators(doc)
-      end
-
-      def make string
-        ns = XML::NodeSet.new
-        ns << XML::Text.new(string)
-        ns
-      end
-
-      def add_decorators(doc)
-        doc.decorators['node'] << Decorators::Hpricot::Node
-        doc.decorators['element'] << Decorators::Hpricot::Node
-        doc.decorators['document'] << Decorators::Hpricot::Node
-        doc.decorators['nodeset'] << Decorators::Hpricot::NodeSet
-        doc.decorate!
-        doc
-      end
-    end
-  end
-  
-  class << self
-    def Hpricot(*args, &block)
-      if block_given?
-        builder = Nokogiri::HTML::Builder.new(&block)
-        Nokogiri::Hpricot.add_decorators(builder.doc)
-      else
-        doc = Nokogiri::HTML.parse(*args)
-        Nokogiri::Hpricot.add_decorators(doc)
-      end
-    end
-  end
-end

data/lib/nokogiri/xml/after_handler.rb

@@ -1,18 +0,0 @@
-module Nokogiri
-  module XML
-    class AfterHandler < BeforeHandler
-      attr_accessor :after_nodes
-
-      def initialize node, original_html
-        super
-        @after_nodes = []
-      end
-
-      def end_element name
-        return unless @original_html =~ /<#{name}/i
-        @after_nodes << @stack.last if @stack.length == 1
-        @stack.pop
-      end
-    end
-  end
-end

data/lib/nokogiri/xml/before_handler.rb

@@ -1,32 +0,0 @@
-module Nokogiri
-  module XML
-    class BeforeHandler < Nokogiri::XML::SAX::Document # :nodoc:
-      def initialize node, original_html
-        @original_html = original_html
-        @node = node
-        @stack = []
-      end
-
-      def start_element name, attrs = []
-        return unless @original_html =~ /<#{name}/i
-        node = Node.new(name)
-        Hash[*attrs].each do |k,v|
-          node[k] = v
-        end
-        node.parent = @stack.last if @stack.length != 0
-        @stack << node
-      end
-
-      def characters string
-        node = @stack.last
-        node.content += string
-      end
-
-      def end_element name
-        return unless @original_html =~ /<#{name}/i
-        @node.add_previous_sibling @stack.last if @stack.length == 1
-        @stack.pop
-      end
-    end
-  end
-end

data/lib/nokogiri/xml/element.rb

@@ -1,6 +0,0 @@
-module Nokogiri
-  module XML
-    class Element < Node
-    end
-  end
-end

data/lib/nokogiri/xml/entity_declaration.rb

@@ -1,9 +0,0 @@
-module Nokogiri
-  module XML
-    class EntityDeclaration < Node
-      def attributes
-        nil
-      end
-    end
-  end
-end

data/nokogiri.gemspec

@@ -1,34 +0,0 @@
-Gem::Specification.new do |s|
-  s.name = %q{nokogiri}
-  s.version = "0.0.0"
-  s.platform = %q{x86-mswin32-60}
-
-  s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
-  s.authors = ["Aaron Patterson"]
-  s.date = %q{2008-10-29}
-  s.description = %q{Nokogiri (鋸) is an HTML, XML, SAX, and Reader parser.}
-  s.email = ["aaronp@rubyforge.org"]
-  s.extra_rdoc_files = ["History.txt", "Manifest.txt", "README.ja.txt", "README.txt"]
-  s.files = ["History.txt", "Manifest.txt", "README.ja.txt", "README.txt", "Rakefile", "ext/nokogiri/extconf.rb", "ext/nokogiri/html_document.c", "ext/nokogiri/html_document.h", "ext/nokogiri/html_sax_parser.c", "ext/nokogiri/html_sax_parser.h", "ext/nokogiri/native.c", "ext/nokogiri/native.h", "ext/nokogiri/xml_cdata.c", "ext/nokogiri/xml_cdata.h", "ext/nokogiri/xml_document.c", "ext/nokogiri/xml_document.h", "ext/nokogiri/xml_dtd.c", "ext/nokogiri/xml_dtd.h", "ext/nokogiri/xml_node.c", "ext/nokogiri/xml_node.h", "ext/nokogiri/xml_node_set.c", "ext/nokogiri/xml_node_set.h", "ext/nokogiri/xml_reader.c", "ext/nokogiri/xml_reader.h", "ext/nokogiri/xml_sax_parser.c", "ext/nokogiri/xml_sax_parser.h", "ext/nokogiri/xml_syntax_error.c", "ext/nokogiri/xml_syntax_error.h", "ext/nokogiri/xml_text.c", "ext/nokogiri/xml_text.h", "ext/nokogiri/xml_xpath.c", "ext/nokogiri/xml_xpath.h", "ext/nokogiri/xml_xpath_context.c", "ext/nokogiri/xml_xpath_context.h", "ext/nokogiri/xslt_stylesheet.c", "ext/nokogiri/xslt_stylesheet.h", "lib/nokogiri.rb", "lib/nokogiri/css.rb", "lib/nokogiri/css/generated_parser.rb", "lib/nokogiri/css/generated_tokenizer.rb", "lib/nokogiri/css/node.rb", "lib/nokogiri/css/parser.rb", "lib/nokogiri/css/parser.y", "lib/nokogiri/css/tokenizer.rb", "lib/nokogiri/css/tokenizer.rex", "lib/nokogiri/css/xpath_visitor.rb", "lib/nokogiri/decorators.rb", "lib/nokogiri/decorators/hpricot.rb", "lib/nokogiri/decorators/hpricot/node.rb", "lib/nokogiri/decorators/hpricot/node_set.rb", "lib/nokogiri/decorators/hpricot/xpath_visitor.rb", "lib/nokogiri/hpricot.rb", "lib/nokogiri/html.rb", "lib/nokogiri/html/builder.rb", "lib/nokogiri/html/document.rb", "lib/nokogiri/html/sax/parser.rb", "lib/nokogiri/version.rb", "lib/nokogiri/xml.rb", "lib/nokogiri/xml/after_handler.rb", "lib/nokogiri/xml/before_handler.rb", "lib/nokogiri/xml/builder.rb", "lib/nokogiri/xml/cdata.rb", "lib/nokogiri/xml/document.rb", "lib/nokogiri/xml/dtd.rb", "lib/nokogiri/xml/node.rb", "lib/nokogiri/xml/node_set.rb", "lib/nokogiri/xml/notation.rb", "lib/nokogiri/xml/reader.rb", "lib/nokogiri/xml/sax.rb", "lib/nokogiri/xml/sax/document.rb", "lib/nokogiri/xml/sax/parser.rb", "lib/nokogiri/xml/syntax_error.rb", "lib/nokogiri/xml/text.rb", "lib/nokogiri/xml/xpath.rb", "lib/nokogiri/xml/xpath_context.rb", "lib/nokogiri/xslt.rb", "lib/nokogiri/xslt/stylesheet.rb", "nokogiri.gemspec", "test/css/test_nthiness.rb", "test/css/test_parser.rb", "test/css/test_tokenizer.rb", "test/css/test_xpath_visitor.rb", "test/files/staff.xml", "test/files/staff.xslt", "test/files/tlm.html", "test/helper.rb", "test/hpricot/files/basic.xhtml", "test/hpricot/files/boingboing.html", "test/hpricot/files/cy0.html", "test/hpricot/files/immob.html", "test/hpricot/files/pace_application.html", "test/hpricot/files/tenderlove.html", "test/hpricot/files/uswebgen.html", "test/hpricot/files/utf8.html", "test/hpricot/files/week9.html", "test/hpricot/files/why.xml", "test/hpricot/load_files.rb", "test/hpricot/test_alter.rb", "test/hpricot/test_builder.rb", "test/hpricot/test_parser.rb", "test/hpricot/test_paths.rb", "test/hpricot/test_preserved.rb", "test/hpricot/test_xml.rb", "test/html/sax/test_parser.rb", "test/html/test_builder.rb", "test/html/test_document.rb", "test/test_convert_xpath.rb", "test/test_nokogiri.rb", "test/test_reader.rb", "test/test_xslt_transforms.rb", "test/xml/sax/test_parser.rb", "test/xml/test_builder.rb", "test/xml/test_cdata.rb", "test/xml/test_document.rb", "test/xml/test_dtd.rb", "test/xml/test_node.rb", "test/xml/test_node_set.rb", "test/xml/test_text.rb", "ext/nokogiri/iconv.dll", "ext/nokogiri/libexslt.dll", "ext/nokogiri/libxml2.dll", "ext/nokogiri/libxslt.dll", "ext/nokogiri/zlib1.dll", "ext/nokogiri/native.so"]
-  s.has_rdoc = true
-  s.homepage = %q{http://github.com/tenderlove/nokogiri/tree/master}
-  s.rdoc_options = ["--main", "README.txt"]
-  s.require_paths = ["lib", "ext"]
-  s.rubyforge_project = %q{nokogiri}
-  s.rubygems_version = %q{1.2.0}
-  s.summary = %q{Nokogiri (鋸) is an HTML, XML, SAX, and Reader parser.}
-  s.test_files = ["test/css/test_nthiness.rb", "test/css/test_parser.rb", "test/css/test_tokenizer.rb", "test/css/test_xpath_visitor.rb", "test/hpricot/test_alter.rb", "test/hpricot/test_builder.rb", "test/hpricot/test_parser.rb", "test/hpricot/test_paths.rb", "test/hpricot/test_preserved.rb", "test/hpricot/test_xml.rb", "test/html/sax/test_parser.rb", "test/html/test_builder.rb", "test/html/test_document.rb", "test/test_convert_xpath.rb", "test/test_nokogiri.rb", "test/test_reader.rb", "test/test_xslt_transforms.rb", "test/xml/sax/test_parser.rb", "test/xml/test_builder.rb", "test/xml/test_cdata.rb", "test/xml/test_document.rb", "test/xml/test_dtd.rb", "test/xml/test_node.rb", "test/xml/test_node_set.rb", "test/xml/test_text.rb"]
-
-  if s.respond_to? :specification_version then
-    current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
-    s.specification_version = 2
-
-    if current_version >= 3 then
-      s.add_development_dependency(%q<hoe>, [">= 1.7.0"])
-    else
-      s.add_dependency(%q<hoe>, [">= 1.7.0"])
-    end
-  else
-    s.add_dependency(%q<hoe>, [">= 1.7.0"])
-  end
-end

data/test/hpricot/files/basic.xhtml

@@ -1,17 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" "DTD/xhtml1-strict.dtd">
-<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
-<head>
-    <title>Sample XHTML</title>
-    <link rel='stylesheet' href='test1.css' />
-    <link rel='stylesheet' href='test2.css' />
-    <link rel='stylesheet' href='test3.css' />
-</head>
-<body id='body1'>
-    <p>Sample XHTML for <a id="link1" href="http://code.whytheluckystiff.net/mouseHole/">MouseHole 2</a>.</p>
-    <p class='ohmy'>Please filter <a id="link2" href="http://hobix.com/">me</a>!</p>
-    <p>The third paragraph</p>
-    <p class="last final"><b>THE FINAL PARAGRAPH</b></p>
-</body>
-</html>
-